arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2112.08281cs.CV
收藏

物体状态检测与物体检测:一个新的数据集和定量实验研究

Detecting Object States vs Detecting Objects: A New Dataset and a Quantitative Experimental Study

Institute of Computer Science FORTH(希腊基础研究与技术基金会计算机科学研究所);University of Crete(克里特大学)

Filippos Gouidis, Theodore Patkos, Antonis Argyros, Dimitris Plexousakis

摘要:

图像中对象状态的检测(状态检测- SD)是一个具有理论和实践重要性的问题,并且它与其他重要的计算机视觉问题(例如动作识别和示能检测)紧密交织在一起。它也与任何需要在动态领域中推理和行动的实体高度相关,例如机器人系统和智能代理。尽管它的重要性,到目前为止,对这个问题的研究是有限的。在本文中,我们试图系统地研究SD问题。首先,我们介绍对象状态检测数据集(OSDD),这是一个新的公开数据集,包含18个对象类别和9个状态类的19,000多个注释。其次,使用用于目标检测(OD)的标准深度学习框架,我们进行了一些适当设计的实验,以深入研究SD问题的行为。这项研究能够在各种情况下建立SD性能的基线,以及与OD相比的相对性能。总体而言,实验结果证实,SD比OD更难,需要开发定制的SD方法来有效地解决这个重大问题。

英文摘要:

The detection of object states in images (State Detection - SD) is a problem of both theoretical and practical importance and it is tightly interwoven with other important computer vision problems, such as action recognition and affordance detection. It is also highly relevant to any entity that needs to reason and act in dynamic domains, such as robotic systems and intelligent agents. Despite its importance, up to now, the research on this problem has been limited. In this paper, we attempt a systematic study of the SD problem. First, we introduce the Object State Detection Dataset (OSDD), a new publicly available dataset consisting of more than 19,000 annotations for 18 object categories and 9 state classes. Second, using a standard deep learning framework used for Object Detection (OD), we conduct a number of appropriately designed experiments, towards an in-depth study of the behavior of the SD problem. This study enables the setup of a baseline on the performance of SD, as well as its relative performance in comparison to OD, in a variety of scenarios. Overall, the experimental outcomes confirm that SD is harder than OD and that tailored SD methods need to be developed for addressing effectively this significant problem.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑